English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a novel method called the Relevance Subject Machine (RSM) to solvethe person re-identification (re-id) problem. RSM falls under the category ofBayesian sparse recovery algorithms and uses the sparse representation of theinput video under a pre-defined dictionary to identify the subject in thevideo. Our approach focuses on the multi-shot re-id problem, which is theprevalent problem in many video analytics applications. RSM captures theessence of the multi-shot re-id problem by constraining the support of thesparse codes for each input video frame to be the same. Our proposed approachis also robust enough to deal with time varying outliers and occlusions byintroducing a sparse, non-stationary noise term in the model error. We providea novel Variational Bayesian based inference procedure along with an intuitiveinterpretation of the proposed update rules. We evaluate our approach overseveral commonly used re-id datasets and show superior performance over currentstate-of-the-art algorithms. Specifically, for ILIDS-VID, a recent large scalere-id dataset, RSM shows significant improvement over all published approaches,achieving an 11.5% (absolute) improvement in rank 1 accuracy over the closestcompeting algorithm considered.

Relevance Subject Machine: A Novel Person Re-identification Framework